HTMLをクリーンアップ

myhtmlclean.py

# -*- coding: utf-8 -*-
# stdlib
import re


LEFT_SPACES = re.compile(r'\s+<')
RIGHT_SPACES = re.compile(r'>\s+')
SCRIPT_TAG = re.compile(r'<script[^>]*>.*?</script>')
COMMENT = re.compile(r'<!--[\s\S]*?-->')


def cleanup(html):
    """
    htmlから余計な要素を除去する
    """
    html = html.replace('\n', ' ') 
    html = LEFT_SPACES.sub(lambda t: ' <', html) 
    html = RIGHT_SPACES.sub(lambda t: '> ', html) 
    html = SCRIPT_TAG.sub(lambda t: '', html)
    html = COMMENT.sub(lambda t: '', html)
    return html